def main(distance_metric, threshold, testmode=False):
starttime = time.time()
#make this flexible in case there are no subfolders
folders = [i for i in os.listdir(pathi) if not i.startswith(".")]
print ", ".join(folders)
print "Items in folders", ", ".join(
[str(len(os.listdir(os.path.join(pathi, f)))) for f in folders])
#folders=['files9_output_0102']#, 'files9_output_0102', 'files9_output_0102', 'files9_output_0102','files9_output_0102', 'files9_output_0102','files9_output_0102', 'files9_output_0102', 'files9_output_0102']
print "We have {} folders".format(len(folders))
featuredict = dictmaker(folders,
threshold,
remove_stopwords=True,
remove_punct=True)
wordmatrix_without_cat, wordmatrix_with_cat, catdicti, filedicti = matrixmachine(
folders, featuredict, testmode, "category1")
wordmatrix_without_cat, wordmatrix_with_cat = ct.matrixstats(
wordmatrix_without_cat,
wordmatrix_with_cat,
distance_metric,
zscores=False,
outlier_removal=True,
outlier_threshold=2,
median_metric='median')
#apply to wordmatrix with cats
x = clustermachine(wordmatrix_without_cat, distance_metric, 4)
#print [(i.name, i.no_of_clusters) for i in x]
excludelist = ['total', 'no_of_categories', 'no_of_clusters', 'no_of_cats']
print "These clusterings have less than 2 clusters\n{}\n\n".format(
"\n".join([str(c.name) for c in x if c.no_of_clusters < 2]))
#PRINTING STUFF
headline = "\n\n-----------\n\n"
print "Working with {} distance metric".format(distance_metric)
#CROSS CLUSTERING COMPARISON
for clustering in [c for c in x if c.no_of_clusters > 1]:
cati = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels)
sili = ct.Clusteringstats(
wordmatrix_with_cat, wordmatrix_without_cat, clustering.name,
clustering.labels).cluster_silhouette(distance_metric)
#GENERAL STATS
print headline, headline, "CLUSTERING CALLED {} HAS {} CLUSTERS".format(
clustering.getname()[1], clustering.no_of_clusters)
print "Its silhouette score is {}".format(str(sili))
stats = ct.Clusteringstats(wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).size_of_clusters()
catstats = ct.Clusteringstats(wordmatrix_with_cat,
wordmatrix_without_cat, clustering.name,
clustering.labels).cats_per_cluster()
for cluster in stats:
print "\nCluster {} contains {} items, {} % of the total".format(
cluster, stats[cluster],
round(
float(stats[cluster]) / len(wordmatrix_without_cat) * 100))
for cat in [i for i in catstats[cluster] if not i in excludelist]:
print "{} items of category {} make up {} % of this cluster".format(
catstats[cluster][cat], "".join(
[i[0] for i in catdicti.items() if i[1] == int(cat)]),
round(catstats[cluster][cat] / catstats[cluster]['total'] *
100))
cats = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels).size_of_categories()
#STATS PER CAT
print headline, "Statistics per category"
for cat in [i for i in cats if not i in excludelist]:
print "\nCategory {} has {} items".format(
"".join([i[0] for i in catdicti.items() if i[1] == int(cat)]),
cats[cat]['total'])
for entry in [
i for i in cats[cat]['cat_per_cluster']
if not i in excludelist
]:
print "{} items or {} percent in cluster {}".format(
cats[cat]['cat_per_cluster'][entry],
round(
float(cats[cat]['cat_per_cluster'][entry]) /
float(cats[cat]['total']) * 100), entry)
#PREDICTIVE FEATURES
print headline, "Strongly predictive features are"
cents = ct.Centroidstats(
wordmatrix_without_cat, clustering.name, clustering.labels,
clustering.centroids).cluster_predictors(featuredict)
if cents:
for diff in cents:
print "\nRaw Scores"
print "Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
diff[0], diff[1], ", ".join([
" : ".join(map(unicode, i[::-1]))
for i in cents[diff]['raw_diff']
][:10]))
print "Zscores"
print "Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
diff[0], diff[1], ", ".join([
" : ".join(map(unicode, i[::-1]))
for i in cents[diff]['zscores_diff']
][:10]))
#PROTOTYPES
print headline, "Here is a typical document for each cluster"
distance = distance_metric
if distance_metric == 'manhattan':
distance = 'cityblock'
print "We set the distance metric to {}".format(distance)
docs = ct.Centroidstats(wordmatrix_without_cat, clustering.name,
clustering.labels,
clustering.centroids).central_documents(
wordmatrix_with_cat, filedicti)
if docs:
for cluster in docs:
print "\nCLUSTER {} \n".format(cluster)
with open(docs[cluster][distance][0]) as f:
print f.read()
if len(docs[cluster][distance]) > 8:
print "\nOther files close by in cluster {}:\n".format(
cluster)
print("{}\n" * 8).format(*docs[cluster][distance][1:9])
print headline, "Comparing clusterings"
for clustering in [c for c in x if c.no_of_clusters > 1]:
print headline, "CLUSTERING CALLED {} HAS {} CLUSTERS".format(
clustering.getname()[0], clustering.no_of_clusters)
print "Its silhouette score is {}".format(
str(
ct.Clusteringstats(
wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).cluster_silhouette(distance_metric)))
#all input does it just concatenate name + cluster # and supply clustering object to similarity measurement
input = [(str(type(i.name)).split(".")[3].rstrip("'>") + "--" +
str(i.no_of_clusters), i) for i in x]
simi = ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input)
options = [
'adjustedrand_sim', 'adjustedmutualinfo_sim', 'jaccard_sim', 'v_sim',
'completeness_sim', 'homogeneity_sim', 'silhouette_score_sim'
]
for o in options:
print "\n---\n"
ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input).similarity_matrix(o)
print "\n---\n"
endtime = time.time()
process = endtime - starttime
print headline, "This took us {} minutes".format(process / 60)
#or do we want to do predictive features and typical document per cluster as well????
os.system('say "your program has finished"')
def main():
starttime = time.time()
folders = [i for i in os.listdir(pathi) if not i.startswith(".")]
print ", ".join(folders)
print ", ".join(
[str(len(os.listdir(os.path.join(pathi, f)))) for f in folders])
folders = [
'files9_output_0102'
] #, 'files9_output_0102', 'files9_output_0102', 'files9_output_0102','files9_output_0102', 'files9_output_0102','files9_output_0102', 'files9_output_0102', 'files9_output_0102']
print "We have {} folders".format(len(folders))
featuredict = dictmaker(folders, 5000)
wordmatrix_without_cat, wordmatrix_with_cat, catdicti = matrixmachine(
folders, featuredict, "category1")
#self.matrix_with_cats=matrix_with_cats #data frame including "gold labels"
#self.matrix_without_cats=matrix_with_cats[:,1:] #data frame without "gold labels"
x = clustermachine(wordmatrix_without_cat, 2)
print[(i.name, i.no_of_clusters) for i in x]
#print [i.name for i in x]
excludelist = ['total', 'no_of_categories', 'no_of_clusters', 'no_of_cats']
for clustering in x:
cati = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels)
sili = ct.Clusteringstats(wordmatrix_with_cat, clustering.name,
clustering.labels).cluster_silhouette()
# print cati.size_of_categories()
print "\n\n-----------\n\nClustering called {} has {} clusters".format(
clustering.getname()[0], clustering.no_of_clusters)
print "Its silhouette score is {}".format(str(sili))
stats = ct.Clusteringstats(wordmatrix_with_cat, clustering.name,
clustering.labels).size_of_clusters()
catstats = ct.Clusteringstats(wordmatrix_with_cat, clustering.name,
clustering.labels).cats_per_cluster()
for cluster in stats:
print "\nCluster {} contains {} items, {} % of the total".format(
cluster, stats[cluster],
round(
float(stats[cluster]) / len(wordmatrix_without_cat) * 100))
for cat in [i for i in catstats[cluster] if not i in excludelist]:
print "{} items of category {} make up {} % of this cluster".format(
catstats[cluster][cat], "".join(
[i[0] for i in catdicti.items() if i[1] == int(cat)]),
round(catstats[cluster][cat] / catstats[cluster]['total'] *
100))
cats = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels).size_of_categories()
print "\n\n-----------\n\nStatistics per category"
for cat in [i for i in cats if not i in excludelist]:
print "\nCategory {} has {} items".format(
"".join([i[0] for i in catdicti.items() if i[1] == int(cat)]),
cats[cat]['total'])
for entry in [
i for i in cats[cat]['cat_per_cluster']
if not i in excludelist
]:
print "{} items or {} percent in cluster {}".format(
cats[cat]['cat_per_cluster'][entry],
round(
float(cats[cat]['cat_per_cluster'][entry]) /
float(cats[cat]['total']) * 100), entry)
print "\n\n-----------\n\nStronly predictive features are"
cents = ct.Centroidstats(
clustering.name, clustering.labels,
clustering.centroids).cluster_predictors(featuredict)
for diff in cents:
print "\n Raw Scores"
print "{} differentiate {} and {}\n".format(
", ".join([
" : ".join(map(str, i[::-1]))
for i in cents[diff]['raw_diff']
]), diff[0], diff[1])
print "Zscores"
print "{} differentiate {} and {}".format(
", ".join([
" : ".join(map(str, i[::-1]))
for i in cents[diff]['zscores_diff']
]), diff[0], diff[1])
"We can also add equivalent features if we want"
"And stems and whatnot"
print "\n\n-----------\n\nHere is a typical document for each cluster"
endtime = time.time()
process = endtime - starttime
print "This took us {} minutes".format(process / 60)
def main(distance_metric, threshold, testmode=False):
starttime = time.time()
#here we read in the featuredict
#create the featuredict from a text file
featuredict = {}
with codecs.open(
'/Users/ps22344/Downloads/chapter2/textfiles/emolist_final.txt',
"r", "utf-8") as inputtext:
for line in inputtext.readlines():
featuredict[line.rstrip("\n")] = 0
print "pre length", len(featuredict)
folders = [i for i in os.listdir(pathi) if not i.startswith(".")]
print ", ".join(folders)
print "Items in folders", ", ".join(
[str(len(os.listdir(os.path.join(pathi, f)))) for f in folders])
print "We have {} folders".format(len(folders))
#here we input the featuredict
wordmatrix_without_cat, wordmatrix_with_cat, catdicti, filedicti = matrixmachine(
folders, featuredict, testmode, "category1")
wordmatrix_without_cat, wordmatrix_with_cat = ct.matrixstats(
wordmatrix_without_cat,
wordmatrix_with_cat,
distance_metric,
zscores=False,
outlier_removal=False,
outlier_threshold=2,
median_metric='median')
np.savetxt('wordmatrix_without_cat.gz', wordmatrix_without_cat)
np.savetxt('wordmatrix_with_cat.gz', wordmatrix_with_cat)
x = clustermachine(wordmatrix_without_cat, distance_metric, 4)
#print [(i.name, i.no_of_clusters) for i in x]
excludelist = ['total', 'no_of_categories', 'no_of_clusters', 'no_of_cats']
print "These clusterings have less than 2 clusters\n{}\n\n".format(
"\n".join([str(c.name) for c in x if c.no_of_clusters < 2]))
#PRINTING STUFF
headline = "\n\n-----------\n\n"
print "Working with {} distance metric".format(distance_metric)
#CROSS CLUSTERING COMPARISON
for clustering in [c for c in x if c.no_of_clusters > 1]:
cati = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels)
print "Categorystats established"
sili = ct.Clusteringstats(
wordmatrix_with_cat, wordmatrix_without_cat, clustering.name,
clustering.labels).cluster_silhouette(distance_metric)
print "Clusteringstats established"
#GENERAL STATS
print headline, headline, "CLUSTERING CALLED {} HAS {} CLUSTERS".format(
clustering.getname()[1], clustering.no_of_clusters)
print "Its silhouette score is {}".format(str(sili))
stats = ct.Clusteringstats(wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).size_of_clusters()
catstats = ct.Clusteringstats(wordmatrix_with_cat,
wordmatrix_without_cat, clustering.name,
clustering.labels).cats_per_cluster()
for cluster in stats:
print "\nCluster {} contains {} items, {} % of the total".format(
cluster, stats[cluster],
round(
float(stats[cluster]) / len(wordmatrix_without_cat) * 100))
for cat in [i for i in catstats[cluster] if not i in excludelist]:
print "{} items of category {} make up {} % of this cluster".format(
catstats[cluster][cat], "".join(
[i[0] for i in catdicti.items() if i[1] == int(cat)]),
round(catstats[cluster][cat] / catstats[cluster]['total'] *
100))
cats = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels).size_of_categories()
#STATS PER CAT
print headline, "Statistics per category"
for cat in [i for i in cats if not i in excludelist]:
print "\nCategory {} has {} items".format(
"".join([i[0] for i in catdicti.items() if i[1] == int(cat)]),
cats[cat]['total'])
for entry in [
i for i in cats[cat]['cat_per_cluster']
if not i in excludelist
]:
print "{} items or {} percent in cluster {}".format(
cats[cat]['cat_per_cluster'][entry],
round(
float(cats[cat]['cat_per_cluster'][entry]) /
float(cats[cat]['total']) * 100), entry)
#PREDICTIVE FEATURES
print headline, "Strongly predictive features are"
cents = ct.Centroidstats(
wordmatrix_without_cat, clustering.name, clustering.labels,
clustering.centroids).cluster_predictors(featuredict)
if cents:
for diff in cents:
print "\nRaw Scores"
print diff
#the two below should return the same results; one was worked over because of unicode issues.
print u"Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
unicode(diff[0]), diff[1], ", ".join([
" : ".join([i, unicode(k)])
for i, k in cents[diff]['raw_diff'][:10]
]))
print "Zscores"
#this is python slice notation: "a[::-1] to reverse a string" ; http://stackoverflow.com/questions/509211/explain-pythons-slice-notation
print u"Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
diff[0], diff[1], ", ".join([
" : ".join(map(unicode, i[::-1]))
for i in cents[diff]['zscores_diff']
][:10]))
#PROTOTYPES
print headline, "Here is a typical document for each cluster"
distance = distance_metric
if distance_metric == 'manhattan':
distance = 'cityblock'
print "We set the distance metric to {}".format(distance)
docs = ct.Centroidstats(wordmatrix_without_cat, clustering.name,
clustering.labels,
clustering.centroids).central_documents(
wordmatrix_with_cat, filedicti)
if docs:
for cluster in docs:
print "\nCLUSTER {} \n".format(cluster)
with open(docs[cluster][distance][0]) as f:
print f.read()
if len(docs[cluster][distance]) > 8:
print "\nOther files close by in cluster {}:\n".format(
cluster)
print("{}\n" * 8).format(*docs[cluster][distance][1:9])
print headline, "Comparing clusterings"
for clustering in [c for c in x if c.no_of_clusters > 1]:
print headline, "CLUSTERING CALLED {} HAS {} CLUSTERS".format(
clustering.getname()[0], clustering.no_of_clusters)
print "Its silhouette score is {}".format(
str(
ct.Clusteringstats(
wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).cluster_silhouette(distance_metric)))
#all input does it just concatenate name + cluster # and supply clustering object to similarity measurement
input = [(str(type(i.name)).split(".")[3].rstrip("'>") + "--" +
str(i.no_of_clusters), i) for i in x]
simi = ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input)
options = [
'adjustedrand_sim', 'adjustedmutualinfo_sim', 'jaccard_sim', 'v_sim',
'completeness_sim', 'homogeneity_sim', 'silhouette_score_sim'
]
for o in options:
print "\n---\n"
ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input).similarity_matrix(o)
print "\n---\n"
endtime = time.time()
process = endtime - starttime
print headline, "This took us {} minutes".format(process / 60)
#or do we want to do predictive features and typical document per cluster as well????
os.system('say "your program has finished"')
def main(distance_metric, testmode=False):
starttime = time.time()
#x=ct.clustermachine(wordmatrix_without_cat,distance_metric,4)
print "These clusterings have less than 2 clusters\n{}\n\n".format(
"\n".join([str(c.name) for c in x if c.no_of_clusters < 2]))
#PRINTING STUFF
headline = "\n\n-----------\n\n"
print "Working with {} distance metric".format(distance_metric)
#v is a number, k a word
excludelist = [
'total', 'no_of_categories', 'no_of_clusters', 'no_of_cats'
] + [
v for k, v in catdicti.items()
if wordmatrix_with_cat[wordmatrix_with_cat[:, 0] == v].shape[0] < 100
]
print "excludelist", excludelist
#CROSS CLUSTERING COMPARISON
for clustering in [c for c in x if c.no_of_clusters > 1]:
cati = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels)
print "Categorystats done"
sili = ct.Clusteringstats(
wordmatrix_with_cat, wordmatrix_without_cat, clustering.name,
clustering.labels).cluster_silhouette(distance_metric)
print "Clusteringstats done"
#GENERAL STATS
print headline, headline, "CLUSTERING CALLED {} HAS {} CLUSTERS".format(
clustering.getname()[1], clustering.no_of_clusters)
print "Its silhouette score is {}".format(str(sili))
stats = ct.Clusteringstats(wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).size_of_clusters()
print "stats done"
catstats = ct.Clusteringstats(wordmatrix_with_cat,
wordmatrix_without_cat, clustering.name,
clustering.labels).cats_per_cluster()
print "catstats done"
for cluster in stats:
print "\nCluster {} contains {} items, {} % of the total".format(
cluster, stats[cluster],
round(
float(stats[cluster]) / len(wordmatrix_without_cat) * 100))
for cat in [i for i in catstats[cluster] if not i in excludelist]:
print "{} items of category {} make up {} % of this cluster".format(
catstats[cluster][cat], "".join(
[i[0] for i in catdicti.items() if i[1] == int(cat)]),
round(catstats[cluster][cat] / catstats[cluster]['total'] *
100))
cats = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels).size_of_categories()
#STATS PER CAT
print headline, "Statistics per category"
for cat in [i for i in cats if not i in excludelist]:
print "\nCategory {} has {} items".format(
"".join([i[0] for i in catdicti.items() if i[1] == int(cat)]),
cats[cat]['total'])
for entry in [
i for i in cats[cat]['cat_per_cluster']
if not i in excludelist
]:
print "{} items or {} percent in cluster {}".format(
cats[cat]['cat_per_cluster'][entry],
round(
float(cats[cat]['cat_per_cluster'][entry]) /
float(cats[cat]['total']) * 100), entry)
# #PREDICTIVE FEATURES
print headline, "Strongly predictive features are"
cents = ct.Centroidstats(
wordmatrix_without_cat, clustering.name, clustering.labels,
clustering.centroids).cluster_predictors(featuredict)
if cents:
for diff in cents:
print "\nRaw Scores"
print "Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
diff[0], diff[1], ", ".join([
" : ".join(map(unicode, i[::-1]))
for i in cents[diff]['raw_diff']
][:10]))
print "Zscores"
print "Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
diff[0], diff[1], ", ".join([
" : ".join(map(unicode, i[::-1]))
for i in cents[diff]['zscores_diff']
][:10]))
#PROTOTYPES
print headline, "Here is a typical document for each cluster"
distance = distance_metric
if distance_metric == 'manhattan':
distance = 'cityblock'
print "We set the distance metric to {}".format(distance)
docs = ct.Centroidstats(wordmatrix_without_cat, clustering.name,
clustering.labels,
clustering.centroids).central_documents(
wordmatrix_with_cat, filedicti)
if docs:
for cluster in docs:
print "\nCLUSTER {} \n".format(cluster)
print docs[cluster][distance]
with open(docs[cluster][distance][0]) as f:
print f.read()
if len(docs[cluster][distance]) > 8:
print "\nOther files close by in cluster {}:\n".format(
cluster)
print("{}\n" * 8).format(*docs[cluster][distance][1:9])
#COMPARING CLUSTERINGS
print headline, "Comparing clusterings"
for clustering in [c for c in x if c.no_of_clusters > 1]:
print headline, "CLUSTERING CALLED {} HAS {} CLUSTERS".format(
clustering.getname()[0], clustering.no_of_clusters)
print "Its silhouette score is {}".format(
str(
ct.Clusteringstats(
wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).cluster_silhouette(distance_metric)))
#all input does it just concatenate name + cluster # and supply clustering object to similarity measurement
input = [(str(type(i.name)).split(".")[3].rstrip("'>") + "--" +
str(i.no_of_clusters), i) for i in x]
simi = ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input)
options = [
'adjustedrand_sim', 'adjustedmutualinfo_sim', 'jaccard_sim', 'v_sim',
'completeness_sim', 'homogeneity_sim', 'silhouette_score_sim'
]
for o in options:
print "\n---\n"
ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input).similarity_matrix(o)
print "\n---\n"
endtime = time.time()
process = endtime - starttime
print headline, "This took us {} minutes".format(process / 60)
def main():
starttime = time.time()
folders = [i for i in os.listdir(pathi) if not i.startswith(".")]
print ", ".join(folders)
print ", ".join(
[str(len(os.listdir(os.path.join(pathi, f)))) for f in folders])
#folders=['files9_output_0102']#, 'files9_output_0102', 'files9_output_0102', 'files9_output_0102','files9_output_0102', 'files9_output_0102','files9_output_0102', 'files9_output_0102', 'files9_output_0102']
print "We have {} folders".format(len(folders))
featuredict = dictmaker(folders, 10000)
wordmatrix_without_cat, wordmatrix_with_cat, catdicti, filedicti = matrixmachine(
folders, featuredict, "category1")
x = clustermachine(wordmatrix_without_cat, 4)
print[(i.name, i.no_of_clusters) for i in x]
#print [i.name for i in x]
excludelist = ['total', 'no_of_categories', 'no_of_clusters', 'no_of_cats']
for clustering in x:
cati = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels)
sili = ct.Clusteringstats(wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).cluster_silhouette()
# print cati.size_of_categories()
headline = "\n\n-----------\n\n"
#GENERAL STATS
print headline, headline, "CLUSTERING CALLED {} HAS {} CLUSTERS".format(
clustering.getname()[0], clustering.no_of_clusters)
print "Its silhouette score is {}".format(str(sili))
stats = ct.Clusteringstats(wordmatrix_with_cat, wordmatrix_without_cat,
clustering.name,
clustering.labels).size_of_clusters()
catstats = ct.Clusteringstats(wordmatrix_with_cat,
wordmatrix_without_cat, clustering.name,
clustering.labels).cats_per_cluster()
for cluster in stats:
print "\nCluster {} contains {} items, {} % of the total".format(
cluster, stats[cluster],
round(
float(stats[cluster]) / len(wordmatrix_without_cat) * 100))
for cat in [i for i in catstats[cluster] if not i in excludelist]:
print "{} items of category {} make up {} % of this cluster".format(
catstats[cluster][cat], "".join(
[i[0] for i in catdicti.items() if i[1] == int(cat)]),
round(catstats[cluster][cat] / catstats[cluster]['total'] *
100))
cats = ct.Categorystats(wordmatrix_with_cat, clustering.name,
clustering.labels).size_of_categories()
#STATS PER CAT
print headline, "Statistics per category"
for cat in [i for i in cats if not i in excludelist]:
print "\nCategory {} has {} items".format(
"".join([i[0] for i in catdicti.items() if i[1] == int(cat)]),
cats[cat]['total'])
for entry in [
i for i in cats[cat]['cat_per_cluster']
if not i in excludelist
]:
print "{} items or {} percent in cluster {}".format(
cats[cat]['cat_per_cluster'][entry],
round(
float(cats[cat]['cat_per_cluster'][entry]) /
float(cats[cat]['total']) * 100), entry)
#PREDICTIVE FEATURES
print headline, "Stronly predictive features are"
cents = ct.Centroidstats(
clustering.name, clustering.labels,
clustering.centroids).cluster_predictors(featuredict)
if cents:
for diff in cents:
print "\nRaw Scores"
print "Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
diff[0], diff[1], ", ".join([
" : ".join(map(str, i[::-1]))
for i in cents[diff]['raw_diff']
][:10]))
print "Zscores"
print "Cluster {} and cluster {} are differentiated by \n{}\n\n\n".format(
diff[0], diff[1], ", ".join([
" : ".join(map(str, i[::-1]))
for i in cents[diff]['zscores_diff']
][:10]))
print "We can also add equivalent features if we want"
print "And stems and whatnot"
#PROTOTYPES
print headline, "Here is a typical document for each cluster"
distance = 'euclidean'
print "We set the distance metric to {}".format(distance)
docs = ct.Centroidstats(clustering.name, clustering.labels,
clustering.centroids).central_documents(
wordmatrix_with_cat, filedicti)
if docs:
for cluster in docs:
print "\nCLUSTER {} \n".format(cluster)
f = open(docs[cluster][distance][0]).read()
print f
#CROSS CLUSTERING COMPARISON
print headline, "Comparing clusterings"
#
input = [(str(type(i.name)).split(".")[3].rstrip("'>"), i) for i in x]
simi = ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input)
options = [
'adjustedrand_sim', 'adjustedmutualinfo_sim', 'jaccard_sim', 'v_sim',
'completeness_sim', 'homogeneity_sim', 'silhouette_score_sim'
]
for o in options:
print "\n---\n"
ct.Clusteringsimilarity(wordmatrix_with_cat, wordmatrix_without_cat,
input).similarity_matrix(o)
print "\n---\n"
endtime = time.time()
process = endtime - starttime
print headline, "This took us {} minutes".format(process / 60)
